regex_pandas_func.py

def match_regex_patt(df, target_col, regex_patt, no_match_value='None'):
    '''Returns regex_patt matches as list.  Case is ignored.'''
    matchList=[]
    cnt = 0
    for idx in df.index:
        m = re.search(regex_patt, df.loc[idx, target_col], flags=re.IGNORECASE) #re.search(pattern, string) gets first match
        if m is not None:
            matchList.append(m.group(1).lower())
        else:
            cnt+=1
            matchList.append(no_match_value)
    print(f'In {target_col}, {cnt} missed matches for regex pattern: {regex_patt}.')
    return matchList